Sponsored by Deepsite.site

Rami Code Review

Created By
Shavakan7 days ago
Rami reviews every pull request for the bugs, logic errors, and risky patterns that AI coding agents commonly leave behind. When it flags something, your agent — Claude Code, Cursor, or Codex — fetches the finding over MCP, fixes it, and pushes; Rami re-reviews until those issues are cleared. A passing Rami check means the PR is free of those common agent flaws — not that it's ready to merge; that call stays yours. Disagree with a finding? Dispute it with evidence and Rami re-evaluates. Free to start — 2 reviews/day, no credit card.
Overview

Rami

Rami Code Review

Works with Claude Code AND Codex. Rami reviews every PR for security, bugs, and performance — then fixes the findings through MCP. You stay in control of what merges.

Rami PR check

Disputing Findings

Not every finding needs a fix. Push back when you have evidence — Rami evaluates the dispute and either accepts it or asks you to fix:

  • False positive — the code is actually correct
  • Framework guarantee — the framework handles this case
  • Intentional design — this is by design, not a mistake
  • Duplicate — the same issue is reported elsewhere

The dispute loop runs in the same session as the review, so accepted disputes drop out and only real issues land in your commits.

Getting Started

1. Install the GitHub App

Install Rami on your repository.

2. Add the marketplace

Claude Code:

/plugin marketplace add rami-code-review/claude-code-marketplace

Codex:

Install the Rami plugin from this repository's Codex marketplace metadata.

3. Install the plugin

Claude Code:

/plugin install rami@rami-code-review

Codex:

Install the rami plugin from the rami-code-review marketplace.

4. Run a review

On a PR branch, run:

/rami:review

Rami fetches the review, walks each finding by priority, and applies fixes (or accepts disputes) until the PR is clean.

Commands

/rami:review

Full review-fix-dispute loop on the current PR branch:

  • Fetches review results
  • Walks findings by priority (blocking → high → medium → low)
  • Fixes each one — or lets you dispute with evidence
  • Commits and pushes
  • Repeats until clean (up to 5 iterations)

/rami:review-status

Check review status without triggering a new review.

/rami:usage

Check remaining quota and credit balance.

Troubleshooting

"No PR found for branch" — push the branch and open a pull request.

"Authentication required" — install the Rami GitHub App on the repo.

Review taking too long?/rami:review-status checks progress without triggering a new review.

License

MIT

Server Config

{
  "mcpServers": {
    "rami": {
      "url": "https://rami.reviews/mcp"
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
WindsurfThe new purpose-built IDE to harness magic
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Serper MCP ServerA Serper MCP Server
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
ChatWiseThe second fastest AI chatbot™
Amap Maps高德地图官方 MCP Server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Tavily Mcp
CursorThe AI Code Editor
Playwright McpPlaywright MCP server
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
DeepChatYour AI Partner on Desktop
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.